R-1187 (c): refuse a .fab import over an installed app that is not running (it merged old and bundle data); R-1189 (d): the off-site proof + integrity check run after a catch-up; unreleased

controller/internal/appexport/r1187c_test.go

@@ -0,0 +1,51 @@
+package appexport
+
+import (
+	"io"
+	"log"
+	"os"
+	"path/filepath"
+	"strings"
+	"testing"
+)
+
+// R-1187 (c): a bundle imported over an app that is installed but NOT running is refused before anything is written —
+// before the fix it „overwrote config in place" and merged the old volume data with the bundle's (proven on 9202
+// 2026-10-22: a marker written after the export survived the import, reported as success).
+// RED-PROOF: without the refusal the job succeeds over the stopped app — seen failing 2026-10-22.
+func TestR1187c_AStoppedAppIsNotImportedOver(t *testing.T) {
+	calls := swapDockerExec(t, func(c dockerCall, stdin io.Reader, stdout io.Writer) (string, error) { return "", nil })
+	tree := t.TempDir()
+	os.MkdirAll(filepath.Join(tree, "config"), 0755)
+	os.WriteFile(filepath.Join(tree, "config", "docker-compose.yml"), []byte("services: {}\n"), 0644)
+	man := &Manifest{Version: ManifestVersion, AppName: "kuma", DisplayName: "Kuma", ConfigFiles: []string{"docker-compose.yml"}}
+	data, err := man.Marshal()
+	if err != nil {
+		t.Fatal(err)
+	}
+	os.WriteFile(filepath.Join(tree, "manifest.json"), data, 0644)
+	fab := filepath.Join(t.TempDir(), "kuma.fab")
+	if err := createTarGz(fab, tree); err != nil {
+		t.Fatal(err)
+	}
+	stacksDir := t.TempDir()
+	stackDir := filepath.Join(stacksDir, "kuma")
+	os.MkdirAll(stackDir, 0755)
+	os.WriteFile(filepath.Join(stackDir, "docker-compose.yml"), []byte("LIVE"), 0644)
+
+	prov := &rtProvider{stackDir: stackDir, stacksDir: stacksDir, deployed: true, running: false}
+	e := NewExporter(prov, log.New(io.Discard, "", 0), "test")
+	if err := e.StartImport(ImportRequest{FABPath: fab}); err != nil {
+		t.Fatalf("StartImport: %v", err)
+	}
+	msg := jobErr(waitJob(t, e))
+	if msg == "" || !strings.Contains(msg, "nem fut") {
+		t.Fatalf("an import over a stopped app must be refused with the reason, got %q", msg)
+	}
+	if b, _ := os.ReadFile(filepath.Join(stackDir, "docker-compose.yml")); string(b) != "LIVE" {
+		t.Fatalf("the app's files were changed: %q", b)
+	}
+	if prov.stopped != 0 || prov.removed != 0 || prov.started || len(*calls) != 0 {
+		t.Fatalf("a refused import must change nothing: stopped=%d removed=%d started=%t docker=%v", prov.stopped, prov.removed, prov.started, *calls)
+	}
+}

controller/internal/appexport/restore.go

@@ -358,6 +358,18 @@ func (e *Exporter) executeImport(req ImportRequest, job *Job) {
 	}
 	e.debugf("existing stack: deployed=%v running=%v", isDeployed, isRunning)
 
+	// R-1187 (c) (data-loss hunt 2026-10-20; proven on 9202 2026-10-22): an import over an app that is installed but
+	// NOT running used to „overwrite config in place" — its volumes were never removed, and `docker cp` only adds and
+	// overwrites, so the result was the old data MERGED with the bundle's (a stale SQLite -wal beside the bundle's .db
+	// is a corruption shape), reported as success. Only a running app's volumes are removed first. So this import is
+	// refused here, before anything is written; the household starts the app (or removes it) and imports again.
+	// Pinned by TestR1187c_AStoppedAppIsNotImportedOver.
+	if isDeployed && !isRunning {
+		e.logger.Printf("[WARN] Import: refused — %s is installed but not running; importing over it would merge the old data with the bundle's (R-1187 c)", manifest.AppName)
+		e.failJob(job, step, "Az alkalmazás telepítve van, de nem fut, ezért a csomagot nem töltjük vissza: a régi adatai összekeveredhetnének a csomagéval. Az alkalmazás érintetlen. Indítsd el (vagy távolítsd el), és próbáld újra.")
+		return
+	}
+
 	if isDeployed {
 		if isRunning {
 			e.logger.Printf("[INFO] Import: removing existing stack %s (with volumes)", manifest.AppName)

controller/internal/nightchain/nightchain.go

@@ -224,10 +224,14 @@ type CatchUp struct {
 	Legs        map[Leg]func(context.Context) error // the leg bodies — WITHOUT the update leg
 	QuiesceBusy func() bool                         // a whole-guest backup holds the apps now
 	Event       func(missedAt time.Time)            // the household's timeline line
-	Logger      *log.Logger
-	Delay       time.Duration
-	Loc         *time.Location
-	Now         func() time.Time
+	// After (R-1189 d) runs once after the legs of a catch-up that ran: the off-site proof (05:30) and the integrity
+	// check (06:00) are daily jobs the scheduler never runs late, so a box that is off at those hours was never
+	// checked — the catch-up is where such a box comes back. nil = nothing.
+	After  func(ctx context.Context)
+	Logger *log.Logger
+	Delay  time.Duration
+	Loc    *time.Location
+	Now    func() time.Time
 	// Sleep waits d or until ctx ends (false). A seam for tests.
 	Sleep func(ctx context.Context, d time.Duration) bool
 
@@ -336,6 +340,10 @@ func (c *CatchUp) run(ctx context.Context, why string) {
 		names = append(names, string(leg))
 	}
 	c.Ledger.markCatchUp(c.now())
+	if c.After != nil {
+		c.Logger.Printf("[INFO] [catch-up] running the after-catch-up checks (the off-site proof and the due-gated integrity check, R-1189 d)")
+		c.After(ctx)
+	}
 	sort.Strings(names)
 	c.Logger.Printf("[INFO] [catch-up] done: %s in %s (missed at %s)", strings.Join(names, ", "),
 		c.now().Sub(start).Round(time.Second), lastW.In(c.Loc).Format("2006-01-02 15:04"))

controller/internal/nightchain/r1189d_test.go

@@ -0,0 +1,45 @@
+package nightchain
+
+import (
+	"context"
+	"sync"
+	"testing"
+)
+
+// R-1189 (d): the after-catch-up checks run once, AFTER every leg of the catch-up (the off-site proof and the
+// integrity check are daily jobs the scheduler never runs late; the catch-up is where a box off at 05:30–06:00 comes
+// back). A box with nothing missed never runs them from here (its 05:30/06:00 jobs do).
+// RED-PROOF: with the After call removed from run(), the first assertion fails — seen failing 2026-10-22.
+func TestR1189d_TheChecksRunAfterTheCatchUpLegs(t *testing.T) {
+	h := newHarness(t, at(1, 12, 0), at(5, 9, 0))
+	h.l.MarkEnded(LegDBDump, at(4, 2, 31))
+	h.l.MarkEnded(LegTier2, at(4, 3, 31))
+	h.l.MarkEnded(LegOffsite, at(4, 4, 20))
+	var mu sync.Mutex
+	var after []int // how many legs had run when After was called
+	h.c.After = func(context.Context) {
+		mu.Lock()
+		after = append(after, len(h.ran))
+		mu.Unlock()
+	}
+	if legs := h.c.Evaluate(context.Background(), "start"); len(legs) != 3 {
+		t.Fatalf("no catch-up scheduled: %v", legs)
+	}
+	h.wait(t)
+	mu.Lock()
+	defer mu.Unlock()
+	if len(after) != 1 || after[0] != 3 {
+		t.Fatalf("After calls %v, want exactly one, after all 3 legs", after)
+	}
+
+	h2 := newHarness(t, at(1, 12, 0), at(5, 11, 0))
+	h2.l.MarkEnded(LegDBDump, at(5, 2, 31))
+	h2.l.MarkEnded(LegTier2, at(5, 3, 31))
+	h2.l.MarkEnded(LegOffsite, at(5, 4, 20))
+	called := false
+	h2.c.After = func(context.Context) { called = true }
+	h2.c.Evaluate(context.Background(), "start")
+	if called {
+		t.Fatal("no catch-up ran, so the after-catch-up checks must not run")
+	}
+}